We Solved Agent Building - The Evolution of Building A Successful Data Science Agent
At Vercel I've built a successful AI data scientist, that has taken the load off of our data team from answering ad-hoc data queries, and fields over 1,200 unique queries a day from just internal Vercelians. I've been building and iterating on it since last september, and it's gone through over 6 different rewrites, the newest one of which has inspired us to build a new agent framework (to be teased during the talk ;) ). I'd talk about why we build agents, how we build agents, and how to build effective agents in today's world. Just prompting, to adding bespoke tooling, to embedding claude code, to file system agents, to skills-based agents, to the new agent harness framework.
About the Harness Engineering Track
Harness Engineering sessions at AI Engineer World's Fair 2026 in San Francisco.
When
Thursday, July 2, 2026
3:20 PM - 3:40 PM·20m
Where
Main Stage
Capacity: 4000 attendees
Sign in to add this talk to your schedule.
Speaker
Andrew Qu
Vercel
@andrewqu
Andrew is the Chief of Software at Vercel, where he leads the company's agent initiatives across product, infrastructure, and internal tooling in the Office of the CTO. He's the creator of skills.sh, the most popular way to discover and install new agent skills, and is building "an agent on every desk" inside Vercel. The most prominent so far is a data science agent that fields 2,000+ questions a day from Vercelians across engineering, finance, and go-to-market. Before Vercel, Andrew founded a Series B AI sales-tech company, and has worked at Meta and early-stage startups alike.